Data Science Orientation

Question 1

What does a Data Scientist do?

Answer 1

So, typically as a data scientist, the majority of our time is spent dealing with data, munging data; doing what we call feature engineering, so taking that raw input

data and transforming it in a way that we can actually provide value.

A great deal of my time is spent cleaning data and getting data ready to actually be good enough to be

trust worthy.

Question 2

What are some key skills you need as a data scientist?

Answer 2

1. Math
2. Statistics
3. Programming R / Python
4. Data Visualization and Modeling
   5.

Question 3

What is the first thing you can do as a data scientist?

Answer 3

I think the best thing that you can do with data is just understand what you have and start asking yourself questions and just start exploring and from there you can make incredible – do incredible things for businesses and organizations to help them drive improvements and whatever it is, that their problems are trying to solve.

Question 4

What are the types of questions you may ask of the data?

Answer 4

1. Descriptive
2. Associative
3. Comparitive
4. Predictive
   5.

Question 5

You are working in Excel with a large table of data that includes a column of student scores.

You want to highlight the scores in the table so you can find the rows for the students who scored the top 10% of grades more easily.

Which Excel visualization should you use?

Answer 5

Conditional Formatting

Question 6

You create a line chart in Excel, showing monthly rainfall levels over a period of 10 years.

You want the chart to indicate whether rainfall is generally rising, falling, or remaining at a consistent level.

What should you add to the chart?

Answer 6

A trendline

Question 7

What is the standard deviation for normal distribution of data?

Answer 7

a normal distribution, 67 percent of your data will fall between plus 1 and minus 1

standard deviations from the mean; 95 to 96 percent fall between plus 2 and minus 2; and

then 99 percent between plus 3 and minus 3

Question 8

What is Standard error?

Answer 8

SE= S/√ n

The standard error is simply the standard deviation divided by the square root of the number of observations that you have.

Now, this is important because when we look at any value that we obtain from any set of data, it’s just an estimate of the population.

Question 9

What is Kurtosis?

Answer 9

Kurtosis is an estimate of the normality of the data; the closer it

is to 0, the more likely the data is normally distributed

Question 10

What is normal for Kurtosis and skewness?

Answer 10

In both cases, values between minus 2 and plus

2 are considered okay for statistical analysis.

Question 11

What is a correlation range?

Answer 11

First, correlations always range from negative 1 to positive 1.

The closer the relationship is to 1, the more in-alignment those variables are, so they move together either in the same direction if it’s a positive correlation, or in opposite

directions if it’s a negative correlation.

Question 12

What is variance?

Answer 12

Variance is simply the measurement of dispersion in the data; how far away is – are each of the values on average from the mean.

Question 13

Good to remember about : Standard Error

Answer 13

The standard error actually gets smaller with the larger number of samples that you have, which is why we take it and we divide it by the square root of N.